GPT-3.5-Turbo、GPT-4、GPT-4o モデルを使用する

import os
from openai import AzureOpenAI

client = AzureOpenAI(
  api_key = os.getenv("AZURE_OPENAI_API_KEY"),  
  api_version = "2024-02-01",
  azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT")
)

response = client.chat.completions.create(
    model="gpt-35-turbo", # model = "deployment_name".
    messages=[
        {"role": "system", "content": "Assistant is a large language model trained by OpenAI."},
        {"role": "user", "content": "Who were the founders of Microsoft?"}
    ]
)

#print(response)
print(response.model_dump_json(indent=2))
print(response.choices[0].message.content)

{
  "id": "chatcmpl-8GHoQAJ3zN2DJYqOFiVysrMQJfe1P",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "Microsoft was founded by Bill Gates and Paul Allen. They established the company on April 4, 1975. Bill Gates served as the CEO of Microsoft until 2000 and later as Chairman and Chief Software Architect until his retirement in 2008, while Paul Allen left the company in 1983 but remained on the board of directors until 2000.",
        "role": "assistant",
        "function_call": null
      },
      "content_filter_results": {
        "hate": {
          "filtered": false,
          "severity": "safe"
        },
        "self_harm": {
          "filtered": false,
          "severity": "safe"
        },
        "sexual": {
          "filtered": false,
          "severity": "safe"
        },
        "violence": {
          "filtered": false,
          "severity": "safe"
        }
      }
    }
  ],
  "created": 1698892410,
  "model": "gpt-35-turbo",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 73,
    "prompt_tokens": 29,
    "total_tokens": 102
  },
  "prompt_filter_results": [
    {
      "prompt_index": 0,
      "content_filter_results": {
        "hate": {
          "filtered": false,
          "severity": "safe"
        },
        "self_harm": {
          "filtered": false,
          "severity": "safe"
        },
        "sexual": {
          "filtered": false,
          "severity": "safe"
        },
        "violence": {
          "filtered": false,
          "severity": "safe"
        }
      }
    }
  ]
}
Microsoft was founded by Bill Gates and Paul Allen. They established the company on April 4, 1975. Bill Gates served as the CEO of Microsoft until 2000 and later as Chairman and Chief Software Architect until his retirement in 2008, while Paul Allen left the company in 1983 but remained on the board of directors until 2000.

import os
import openai
openai.api_type = "azure"
openai.api_version = "2024-02-01" 
openai.api_base = os.getenv("AZURE_OPENAI_ENDPOINT")  # Your Azure OpenAI resource's endpoint value.
openai.api_key = os.getenv("AZURE_OPENAI_API_KEY")

response = openai.ChatCompletion.create(
    engine="gpt-35-turbo", # The deployment name you chose when you deployed the GPT-3.5-Turbo or GPT-4 model.
    messages=[
        {"role": "system", "content": "Assistant is a large language model trained by OpenAI."},
        {"role": "user", "content": "Who were the founders of Microsoft?"}
    ]
)

print(response)

# To print only the response content text:
# print(response['choices'][0]['message']['content'])

出力

読みやすくするために、JSON の書式設定が人為的に追加されました。

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "The founders of Microsoft are Bill Gates and Paul Allen. They co-founded the company in 1975.",
        "role": "assistant"
      }
    }
  ],
  "created": 1679014551,
  "id": "chatcmpl-6usfn2yyjkbmESe3G4jaQR6bsScO1",
  "model": "gpt-3.5-turbo-0301",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 86,
    "prompt_tokens": 37,
    "total_tokens": 123
  }
}

import os
from openai import AzureOpenAI

client = AzureOpenAI(
  api_key = os.getenv("AZURE_OPENAI_API_KEY"),  
  api_version = "2024-02-01",
  azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT")  # Your Azure OpenAI resource's endpoint value.
)

conversation=[{"role": "system", "content": "You are a helpful assistant."}]

while True:
    user_input = input("Q:")      
    conversation.append({"role": "user", "content": user_input})

    response = client.chat.completions.create(
        model="gpt-35-turbo", # model = "deployment_name".
        messages=conversation
    )

    conversation.append({"role": "assistant", "content": response.choices[0].message.content})
    print("\n" + response.choices[0].message.content + "\n")

import os
import openai
openai.api_type = "azure"
openai.api_version = "2024-02-01" 
openai.api_base = os.getenv("AZURE_OPENAI_ENDPOINT")  # Your Azure OpenAI resource's endpoint value.
openai.api_key = os.getenv("AZURE_OPENAI_API_KEY")

conversation=[{"role": "system", "content": "You are a helpful assistant."}]

while True:
    user_input = input()      
    conversation.append({"role": "user", "content": user_input})

    response = openai.ChatCompletion.create(
        engine="gpt-35-turbo", # The deployment name you chose when you deployed the GPT-35-turbo or GPT-4 model.
        messages=conversation
    )

    conversation.append({"role": "assistant", "content": response["choices"][0]["message"]["content"]})
    print("\n" + response['choices'][0]['message']['content'] + "\n")

import tiktoken
import os
from openai import AzureOpenAI

client = AzureOpenAI(
  api_key = os.getenv("AZURE_OPENAI_API_KEY"),  
  api_version = "2024-02-01",
  azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT")  # Your Azure OpenAI resource's endpoint value.
)

system_message = {"role": "system", "content": "You are a helpful assistant."}
max_response_tokens = 250
token_limit = 4096
conversation = []
conversation.append(system_message)

def num_tokens_from_messages(messages, model="gpt-3.5-turbo-0613"):
    """Return the number of tokens used by a list of messages."""
    try:
        encoding = tiktoken.encoding_for_model(model)
    except KeyError:
        print("Warning: model not found. Using cl100k_base encoding.")
        encoding = tiktoken.get_encoding("cl100k_base")
    if model in {
        "gpt-3.5-turbo-0613",
        "gpt-3.5-turbo-16k-0613",
        "gpt-4-0314",
        "gpt-4-32k-0314",
        "gpt-4-0613",
        "gpt-4-32k-0613",
        }:
        tokens_per_message = 3
        tokens_per_name = 1
    elif model == "gpt-3.5-turbo-0301":
        tokens_per_message = 4  # every message follows <|start|>{role/name}\n{content}<|end|>\n
        tokens_per_name = -1  # if there's a name, the role is omitted
    elif "gpt-3.5-turbo" in model:
        print("Warning: gpt-3.5-turbo may update over time. Returning num tokens assuming gpt-3.5-turbo-0613.")
        return num_tokens_from_messages(messages, model="gpt-3.5-turbo-0613")
    elif "gpt-4" in model:
        print("Warning: gpt-4 may update over time. Returning num tokens assuming gpt-4-0613.")
        return num_tokens_from_messages(messages, model="gpt-4-0613")
    else:
        raise NotImplementedError(
            f"""num_tokens_from_messages() is not implemented for model {model}."""
        )
    num_tokens = 0
    for message in messages:
        num_tokens += tokens_per_message
        for key, value in message.items():
            num_tokens += len(encoding.encode(value))
            if key == "name":
                num_tokens += tokens_per_name
    num_tokens += 3  # every reply is primed with <|start|>assistant<|message|>
    return num_tokens
while True:
    user_input = input("Q:")      
    conversation.append({"role": "user", "content": user_input})
    conv_history_tokens = num_tokens_from_messages(conversation)

    while conv_history_tokens + max_response_tokens >= token_limit:
        del conversation[1] 
        conv_history_tokens = num_tokens_from_messages(conversation)

    response = client.chat.completions.create(
        model="gpt-35-turbo", # model = "deployment_name".
        messages=conversation,
        temperature=0.7,
        max_tokens=max_response_tokens
    )


    conversation.append({"role": "assistant", "content": response.choices[0].message.content})
    print("\n" + response.choices[0].message.content + "\n")

import tiktoken
import openai
import os

openai.api_type = "azure"
openai.api_version = "2024-02-01" 
openai.api_base = os.getenv("AZURE_OPENAI_ENDPOINT")  # Your Azure OpenAI resource's endpoint value.
openai.api_key = os.getenv("AZURE_OPENAI_API_KEY")

system_message = {"role": "system", "content": "You are a helpful assistant."}
max_response_tokens = 250
token_limit = 4096
conversation = []
conversation.append(system_message)

def num_tokens_from_messages(messages, model="gpt-3.5-turbo-0613"):
    """Return the number of tokens used by a list of messages."""
    try:
        encoding = tiktoken.encoding_for_model(model)
    except KeyError:
        print("Warning: model not found. Using cl100k_base encoding.")
        encoding = tiktoken.get_encoding("cl100k_base")
    if model in {
        "gpt-3.5-turbo-0613",
        "gpt-3.5-turbo-16k-0613",
        "gpt-4-0314",
        "gpt-4-32k-0314",
        "gpt-4-0613",
        "gpt-4-32k-0613",
        }:
        tokens_per_message = 3
        tokens_per_name = 1
    elif model == "gpt-3.5-turbo-0301":
        tokens_per_message = 4  # every message follows <|start|>{role/name}\n{content}<|end|>\n
        tokens_per_name = -1  # if there's a name, the role is omitted
    elif "gpt-3.5-turbo" in model:
        print("Warning: gpt-3.5-turbo may update over time. Returning num tokens assuming gpt-3.5-turbo-0613.")
        return num_tokens_from_messages(messages, model="gpt-3.5-turbo-0613")
    elif "gpt-4" in model:
        print("Warning: gpt-4 may update over time. Returning num tokens assuming gpt-4-0613.")
        return num_tokens_from_messages(messages, model="gpt-4-0613")
    else:
        raise NotImplementedError(
            f"""num_tokens_from_messages() is not implemented for model {model}."""
        )
    num_tokens = 0
    for message in messages:
        num_tokens += tokens_per_message
        for key, value in message.items():
            num_tokens += len(encoding.encode(value))
            if key == "name":
                num_tokens += tokens_per_name
    num_tokens += 3  # every reply is primed with <|start|>assistant<|message|>
    return num_tokens

while True:
    user_input = input("")     
    conversation.append({"role": "user", "content": user_input})
    conv_history_tokens = num_tokens_from_messages(conversation)

    while conv_history_tokens + max_response_tokens >= token_limit:
        del conversation[1] 
        conv_history_tokens = num_tokens_from_messages(conversation)

    response = openai.ChatCompletion.create(
        engine="gpt-35-turbo", # The deployment name you chose when you deployed the GPT-35-Turbo or GPT-4 model.
        messages=conversation,
        temperature=0.7,
        max_tokens=max_response_tokens,
    )

    conversation.append({"role": "assistant", "content": response['choices'][0]['message']['content']})
    print("\n" + response['choices'][0]['message']['content'] + "\n")